nvme: fix handling single range discard request

When investigating one customer report on warning in nvme_setup_discard,
we observed the controller(nvme/tcp) actually exposes
queue_max_discard_segments(req->q) == 1.

Obviously the current code can't handle this situation, since contiguity
merge like normal RW request is taken.

Fix the issue by building range from request sector/nr_sectors directly.

Fixes: b35ba01 ("nvme: support ranged discard requests")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

drivers/nvme/host/core.c

@@ -781,16 +781,26 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 		range = page_address(ns->ctrl->discard_page);
 	}
 
-	__rq_for_each_bio(bio, req) {
-		u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector);
-		u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
-
-		if (n < segments) {
-			range[n].cattr = cpu_to_le32(0);
-			range[n].nlb = cpu_to_le32(nlb);
-			range[n].slba = cpu_to_le64(slba);
+	if (queue_max_discard_segments(req->q) == 1) {
+		u64 slba = nvme_sect_to_lba(ns, blk_rq_pos(req));
+		u32 nlb = blk_rq_sectors(req) >> (ns->lba_shift - 9);
+
+		range[0].cattr = cpu_to_le32(0);
+		range[0].nlb = cpu_to_le32(nlb);
+		range[0].slba = cpu_to_le64(slba);
+		n = 1;
+	} else {
+		__rq_for_each_bio(bio, req) {
+			u64 slba = nvme_sect_to_lba(ns, bio->bi_iter.bi_sector);
+			u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
+
+			if (n < segments) {
+				range[n].cattr = cpu_to_le32(0);
+				range[n].nlb = cpu_to_le32(nlb);
+				range[n].slba = cpu_to_le64(slba);
+			}
+			n++;
 		}
-		n++;
 	}
 
 	if (WARN_ON_ONCE(n != segments)) {